## The problem

for example: The word 'abandon', the voice like you cut off the letter a. He just said 'bandon'. The problem occurs when you use AndrewMultilingualNeural, en-US, and only one word.

## The fix

[LinZhang-Support (commenter)]: This was a backend bug on Microsoft's side, not your code: single-word synthesis with AndrewMultilingualNeural (en-US) clipped the first letter. It was fixed with an updated voice model, first in eastus, with other regions following (no December deployments, ready mid January). If you still hear it, check which region your Speech resource is deployed in.